Comparative Analysis of YOLO11, Vision Transformer (ViT), EfficientNet-V2, and Swin Transformer

This paper compared four modern computer vision architectures: YOLO11, Vision Transformer (ViT), EfficientNet-V2, and Swin Transformer. The study showed that YOLO11 performs efficiently in real-time object detection, while EfficientNet-V2 provides lightweight and computationally efficient image classification. ViT and Swin Transformer demonstrated strong contextual understanding and scalability through attention mechanisms. The comparison highlights that CNN-based models are suitable for real-time and lightweight applications, whereas Transformer-based architectures are more effective for large-scale visual understanding tasks. Future computer vision systems are expected to combine the advantages of both CNN and Transformer architectures for improved performance and efficiency.

1. Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You Only Look Once: Unified Real-Time Object Detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE Press, Las Vegas (2016) 779–788 2. Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D.: An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In: International Conference on Learning Representations. Springer, Vienna (2021) 1–21 3. Tan, M., Le, Q.: EfficientNetV2: Smaller Models and Faster Training. In: Proceedings of the International Conference on Machine Learning. PMLR, Virtual Conference (2021) 10096–10106 4.  Liu, Z., Lin, Y., Cao, Y., Hu, H.: Swin Transformer: Hierarchical Vision Transformer using Shifted Windows. In: Proceedings of the IEEE International Conference on Computer Vision. IEEE Press, Montreal (2021) 9992–10002 5. He, K., Zhang, X., Ren, S., Sun, J.: Deep Residual Learning for Image Recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE Press, Las Vegas (2016) 770–778 6.  Simonyan, K., Zisserman, A.: Very Deep Convolutional Networks for Large-Scale Image Recognition. Int. Conf. Learn. Represent. 1 (2015) 1–14 7. Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. IEEE Trans. Pattern Anal. Mach. Intell. 39 (2017) 1137–1149 8. Howard, A., Sandler, M., Chu, G., Chen, L.: Searching for MobileNetV3. In: Proceedings of the IEEE International Conference on Computer Vision. IEEE Press, Seoul (2019) 1314–1324 9.  Krizhevsky, A., Sutskever, I., Hinton, G.: ImageNet Classification with Deep Convolutional Neural Networks. Commun. ACM 60 (2017) 84–90 Bochkovskiy, A., Wang, C., Liao, H.: YOLOv4: Optimal Speed and Accuracy of Object Detection. arXiv Preprint arXiv:2004.10934 (2020) 1–17